CN108556682A - Driving range prediction method, device and equipment - Google Patents
Driving range prediction method, device and equipment Download PDFInfo
- Publication number
- CN108556682A CN108556682A CN201810294117.3A CN201810294117A CN108556682A CN 108556682 A CN108556682 A CN 108556682A CN 201810294117 A CN201810294117 A CN 201810294117A CN 108556682 A CN108556682 A CN 108556682A
- Authority
- CN
- China
- Prior art keywords
- continual mileage
- data
- characteristic
- mean temperature
- segment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000004364 calculation method Methods 0.000 claims abstract description 30
- 238000000605 extraction Methods 0.000 claims description 30
- 230000006855 networking Effects 0.000 claims description 30
- 238000011084 recovery Methods 0.000 claims description 16
- 238000004140 cleaning Methods 0.000 claims description 12
- 238000010219 correlation analysis Methods 0.000 claims description 10
- 230000002596 correlated effect Effects 0.000 claims description 8
- 238000005520 cutting process Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013075 data extraction Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000010438 heat treatment Methods 0.000 claims 2
- 238000012549 training Methods 0.000 abstract description 9
- 238000004422 calculation algorithm Methods 0.000 description 16
- 238000004458 analytical method Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 5
- 241001269238 Data Species 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 230000005611 electricity Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000001737 promoting effect Effects 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 238000000205 computational method Methods 0.000 description 3
- 230000000875 corresponding effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004378 air conditioning Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L15/00—Methods, circuits, or devices for controlling the traction-motor speed of electrically-propelled vehicles
- B60L15/20—Methods, circuits, or devices for controlling the traction-motor speed of electrically-propelled vehicles for control of the vehicle or its driving motor to achieve a desired performance, e.g. speed, torque, programmed variation of speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L2260/00—Operating Modes
- B60L2260/40—Control modes
- B60L2260/50—Control modes by future state prediction
- B60L2260/52—Control modes by future state prediction drive range estimation, e.g. of estimation of available travel distance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/72—Electric energy management in electromobility
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a driving range prediction method, a driving range prediction device and driving range prediction equipment, wherein the driving range prediction method comprises the following steps: dividing effective travel segments from effective data in the Internet of vehicles pool, and analyzing and extracting relevant characteristic signals, wherein the effective travel segments refer to travel segments with vehicle travel speed greater than zero; calculating according to the characteristic signals to obtain a plurality of characteristic indexes; constructing a regression model of the characteristic indexes, and training the regression model by using the data of the characteristic signals to obtain the weight values of the characteristic indexes; constructing a driving range calculation formula according to the weight value; and substituting the trial value of the characteristic index into the driving range calculation formula to obtain the driving range. According to the driving range prediction method, model training is performed based on a large amount of historical data, and the most relevant characteristic values influencing the driving range are extracted, so that the prediction accuracy is improved, and the prediction precision is improved.
Description
Technical field
The present invention relates to electric vehicle continual mileage calculating field more particularly to a kind of continual mileage prediction technique, devices
And equipment.
Background technology
In pure electric vehicle actual moving process, battery continual mileage can be and existing continuous by various such environmental effects
Method for Calculate Mileage is sailed to be predicted according only to hundred kilometers of power consumptions, do not consider current environment and service condition etc. it is a variety of because
Influence of the element to continual mileage, while existing continual mileage computational methods are not directed to mass data and carry out model training, meter
Calculate precision it is not high, cause client perception to remaining continual mileage have relatively large deviation with actual travel mileage.
Invention content
In order to solve the above technical problem, the present invention provides a kind of continual mileage prediction technique, device and equipment, solve
Continual mileage calculates inaccurate problem.
One side according to the present invention provides a kind of continual mileage prediction technique, including：
Effective travel segment is divided from the valid data in car networking pond, and analyzes extraction correlated characteristic signal, it is described
Effective travel segment refers to the traveling segment that Vehicle Speed is more than zero；
Multiple characteristic indexs are calculated according to the characteristic signal；
The regression model for building the characteristic index instructs the regression model using the data of the characteristic signal
Practice, obtains the weighted value of the characteristic index；
Continual mileage calculation formula is built according to the weighted value；
The trial value of the characteristic index is substituted into the continual mileage calculation formula, obtains continual mileage.
Optionally, effective travel segment is divided in the valid data in the pond from car networking, and it is related to analyze extraction
Before the step of characteristic signal, the method further includes：
From the data sample extracted in car networking pond in vehicle travel；
The data sample is cleaned to obtain valid data.
Optionally, the step of being cleaned to obtain valid data to the data sample include：
Missing values, exceptional value and the repetition record cleaned in the data sample obtains valid data.
Optionally, effective travel segment is divided from the valid data in car networking pond, and analyzes extraction correlated characteristic letter
Number the step of include：
Segment cutting is carried out to vehicle travel to divide, and determines effective travel segment；
Correlation analysis is carried out to the data in the effective travel segment, obtains multiple feature letters for influencing continual mileage
Number.
Optionally, the characteristic signal includes：Power battery charging electric current, power battery charging voltage, power battery are put
Electric current, power battery discharge voltage, driving motor current torque, driving motor current rotating speed, mileage travelled, speed, the time,
Power battery charged state (State of Charge, abbreviation SOC), automobile positive temperature coefficient (Positive Temperature
Coefficient, abbreviation PTC) heater status, electric theft-proof system (Electronic Article Surveillance,
Abbreviation EAS) state, battery mean temperature and environment mean temperature.
Optionally, the characteristic index includes：Energy recovery rate, hundred kilometers of powers of motor, hypervelocity rate, the charged shape of starting
State, state-of-charge variable quantity, automobile positive temperature coefficient ptc heater time accounting, electric theft-proof system EAS times accounting, electricity
Pond mean temperature, environment mean temperature, road conditions average speed and mileage travelled.
Optionally, the continual mileage calculation formula is：
Y=a+b1x1+b2x2+b3x3+...b10x10；
Wherein, y indicates that continual mileage, a indicate the weighted value of mileage travelled；x1~x10Energy recovery rate, hundred are indicated respectively
Kilometer power of motor, hypervelocity rate, starting state-of-charge, state-of-charge variable quantity, automobile positive temperature coefficient ptc heater time account for
Than, electric theft-proof system EAS times accounting, battery mean temperature, environment mean temperature and road conditions average speed；b1~b10Point
It Biao Shi not energy recovery rate, hundred kilometers of powers of motor, hypervelocity rate, starting state-of-charge, state-of-charge variable quantity, the positive temperature of automobile
FACTOR P TC heater times accounting, electric theft-proof system EAS times accounting, battery mean temperature, environment mean temperature and road
The weighted value of condition average speed.
Other side according to the present invention provides a kind of continual mileage prediction meanss, including：
Signal extraction module for dividing effective travel segment from the valid data in car networking pond, and analyzes extraction
Correlated characteristic signal, the effective travel segment refer to the traveling segment that Vehicle Speed is more than zero；
First computing module, for multiple characteristic indexs to be calculated according to the characteristic signal；
First structure module, the regression model for building the characteristic index utilize the data pair of the characteristic signal
The regression model is trained, and obtains the weighted value of the characteristic index；
Second structure module, for building continual mileage calculation formula according to the weighted value；
Second computing module is obtained for the trial value of the characteristic index to be substituted into the continual mileage calculation formula
Continual mileage.
Optionally, the continual mileage prediction meanss further include：
Data extraction module is used for from the data sample extracted in car networking pond in vehicle travel；
Cleaning module, for being cleaned to obtain valid data to the data sample.
Optionally, the cleaning module is specifically used for：
Missing values, exceptional value and the repetition record cleaned in the data sample obtains valid data.
Optionally, the signal extraction module includes：
Segment division unit divides for carrying out segment cutting to vehicle travel, determines effective travel segment；
It is continuous to obtain multiple influences for carrying out correlation analysis to the data in the effective travel segment for extraction unit
Sail the characteristic signal of mileage.
Optionally, the characteristic signal includes：Power battery charging electric current, power battery charging voltage, power battery are put
Electric current, power battery discharge voltage, driving motor current torque, driving motor current rotating speed, mileage travelled, speed signal,
Time, power battery charged state SOC, automobile positive temperature coefficient ptc heater state, electric theft-proof system EAS states, battery
Mean temperature and environment mean temperature.
Optionally, the characteristic index includes：Energy recovery rate, hundred kilometers of powers of motor, hypervelocity rate, the charged shape of starting
State, state-of-charge variable quantity, automobile positive temperature coefficient ptc heater time accounting, electric theft-proof system EAS times accounting, electricity
Pond mean temperature, environment mean temperature, road conditions average speed and mileage travelled.
Optionally, the continual mileage calculation formula is：
Y=a+b1x1+b2x2+b3x3+...b10x10；
Wherein, y indicates that continual mileage, a indicate the weighted value of mileage travelled；x1~x10Energy recovery rate, hundred are indicated respectively
Kilometer power of motor, hypervelocity rate, starting state-of-charge, state-of-charge variable quantity, automobile positive temperature coefficient ptc heater time account for
Than, electric theft-proof system EAS times accounting, battery mean temperature, environment mean temperature and road conditions average speed；b1~b10Point
It Biao Shi not energy recovery rate, hundred kilometers of powers of motor, hypervelocity rate, starting state-of-charge, state-of-charge variable quantity, the positive temperature of automobile
FACTOR P TC heater times accounting, electric theft-proof system EAS times accounting, battery mean temperature, environment mean temperature and road
The weighted value of condition average speed.
Another aspect according to the present invention, provides a kind of pre- measurement equipment of continual mileage, including processor, memory and
It is stored in the computer program that can be run on the memory and on the processor, the computer program is by the processing
The step of device realizes above-mentioned continual mileage prediction technique when executing.
The advantageous effect of the embodiment of the present invention is：
Continual mileage prediction technique in said program influences driving by being determined on the data mining of car networking big data
The major parameter of mileage deviation carries out regression model training based on a large amount of historical datas, promotes predictablity rate, in conjunction with current consumption
Electric factor data carries out recurrence calculating, it can be deduced that best continual mileage predicted value improves precision of prediction.
Description of the drawings
Fig. 1 shows the flow charts of the continual mileage prediction technique of the embodiment of the present invention；
Fig. 2 indicates the idiographic flow schematic diagram of the continual mileage prediction technique of the embodiment of the present invention；
Fig. 3 indicates the structure diagram of the continual mileage prediction meanss of the embodiment of the present invention；
Fig. 4 indicates the concrete structure block diagram of the continual mileage prediction meanss of the embodiment of the present invention.
Specific implementation mode
Exemplary embodiment of the present invention is more fully described below with reference to accompanying drawings.Although showing the present invention in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the present invention without should be by embodiments set forth here
It is limited.It is to be able to be best understood from the present invention on the contrary, providing these embodiments, and can be by the scope of the present invention
Completely it is communicated to those skilled in the art.
As shown in Figure 1, the embodiment provides a kind of continual mileage prediction techniques, including：
Step 11 divides effective travel segment from the valid data in car networking pond, and analyzes extraction correlated characteristic letter
Number, the effective travel segment refers to the traveling segment that Vehicle Speed is more than zero；
In the embodiment, the valid data refer in car networking pond all data through missing values handle, outlier processing
And the data obtained after the data cleansings such as record processing are repeated, the effective travel segment refers to that Vehicle Speed is more than zero
Traveling segment.After marking off effective travel segment in valid data, analysis is carried out to the data in effective travel segment and is carried
Relevant characteristic signal is taken out, i.e., the data information of vehicle really when driving is extracted from valid data, by these data
Information, which carries out correlation analysis, can obtain influencing the characteristic signal of continual mileage, to predict continual mileage, with more representative
Property, be conducive to the accuracy rate for promoting prediction.
Specifically, the characteristic signal includes：Power battery charging electric current, power battery charging voltage, power battery are put
Electric current, power battery discharge voltage, driving motor current torque, driving motor current rotating speed, mileage travelled, speed, the time,
Power battery charged state SOC, automobile positive temperature coefficient ptc heater state, electric theft-proof system EAS states, battery are average
Temperature and environment mean temperature.
Step 12 calculates multiple characteristic indexs according to the characteristic signal；
Specifically, the characteristic index includes：Energy recovery rate, hundred kilometers of powers of motor, hypervelocity rate, the charged shape of starting
State, state-of-charge variable quantity, automobile positive temperature coefficient ptc heater time accounting, electric theft-proof system EAS times accounting, electricity
Pond mean temperature, environment mean temperature, road conditions average speed and mileage travelled.
The characteristic index is to calculate the influence factor being affected to continual mileage, and the characteristic index is by effective row
Characteristic signal in journey segment is calculated, and the computational methods that characteristic index is calculated according to characteristic signal are as shown in the table：
The regression model of step 13, the structure characteristic index, using the data of the characteristic signal to the regression model
It is trained, obtains the weighted value of the characteristic index；
Step 14 builds continual mileage calculation formula according to the weighted value；
The trial value of the characteristic index is substituted into the continual mileage calculation formula by step 15, obtains continual mileage.
In the embodiment, it is contemplated that the shadow of other characteristic indexs can not be rejected when the correction factor of extraction single feature index
It rings, such as when air-conditioning unlatching, the other factors such as driver style, environment temperature and road conditions can all influence in current driving
Journey, so continual mileage prediction is carried out using regression combination model.Regression combination model algorithm is approximate correct based on probability
Learning model under a kind of boosting algorithm for proposing.In regression problem, built-up pattern is divided by changing the weights of training sample
Cloth learns multiple weak recurrence devices, and these is returned to device and carries out linear combination, constitutes one strong recurrence device, improves and return performance.
Device is wherein returned by force and can be regarded as the high algorithm of regression forecasting accuracy, and weak recurrence device can be regarded as the low algorithm of regression accuracy.
The characteristics of regression combination model algorithm is to learn a basic recurrence device (i.e. weak recurrence device) every time by iteration.Each iteration
In, it improves those and is returned the weights of device bigger error data sample by previous round, and reduce those and be predicted the small data of error
The weights of sample.Last algorithm returns device using the basic linear combination for returning device as strong, wherein the base small to error rate is returned
This recurrence device is with big weights, to the big basic recurrence device of recurrence error rate with small weights.
The sample that the program trains characteristic index as regression model, using the data of the characteristic signal to returning mould
Type is trained, and can obtain the proportion that different characteristic index accounts in mileage travelled, the i.e. weight of characteristic index, the feature
The weight of index is the coefficient in continual mileage calculation formula, it is known that the coefficient in continual mileage calculation formula can obtain
The function formula of continual mileage, when carrying out continual mileage prediction, it would be desirable to described in the trial value of the characteristic index of consideration substitutes into
Continual mileage calculation formula, you can obtain comprising the continual mileage under various factors.
The continual mileage prediction technique compared to the prior art according to hundred kilometers of power consumptions carry out prediction continual mileage, the party
Method carries out analysis modeling using big data platform to a large amount of historical datas, can significantly reduce the calculating of electric vehicle continual mileage
Deviation carries out recurrence calculating in conjunction with current power consumption factor data, obtains best continual mileage predicted value, improve precision of prediction.
Specifically, as shown in Fig. 2, before the step 11, the method further includes：
Step 100, from car networking pond extract vehicle travel in data sample；
Step 101 is cleaned to obtain valid data to the data sample.
In the embodiment, data pick-up and data cleansing are carried out based on car networking big data platform, taken out from car networking pond
Take the data sample in vehicle travel that increment extraction mechanism, increment extraction can be utilized to be carried out by the way of comparing timestamp,
The timestamp field of maximum time stamp and extraction source table when extraction process was extracted by comparing system time or source table last time
Value determine to extract which data.
Specifically, the step of being cleaned to obtain valid data to the data sample includes：Clean the data sample
In missing values, exceptional value and repeat record obtain valid data.
Wherein, the method for the missing values cleaned in the data sample is：Average value, maximum are generally used for missing values
Value, minimum value are replaced, but for car networking data rolling average may be used herein due to the particularity of time series
Algorithm, filtering algorithm or according to business rule come the value for missing of substituting, to achieve the purpose that cleaning.
Detection and cleaning method for exceptional value are：Possible error value or exception are identified with the method for statistical analysis
Value can also use simple rule library (common-sense rule, business if the value of distribution or regression equation is not abided by variance analysis, identification
Ad hoc rules etc.) check data value, or detect and clear up data using constraining between different attribute, external data.
It repeats the detection recorded and cleaning method is：The identical record of attribute value is considered as repeating to record in database,
By judging whether the attribute value between record is whether equal equal to detect record, and equal record merges into a record, i.e.,
Merge or removes.
As shown in Fig. 2, step 11 includes：
Step 111 carries out vehicle travel segment cutting division, determines effective travel segment；
Step 112 carries out correlation analysis to the data in the effective travel segment, obtains multiple influence continual mileages
Characteristic signal.
In the embodiment, due in car networking data, owning with what is do not travelled including vehicle travels within a period
Data, within this time, the segment of vehicle traveling can be solely a part, be drawn by carrying out segment cutting to vehicle travel
Point, it may be determined that the segment that vehicle really travels, i.e. effective travel segment, extraction effective travel segment includes out of valid data
Data, then the data that include on effective travel segment carry out correlation analysis and can obtain influencing the feature of continual mileage believing
Number, according to characteristic signal analysis characteristic index is calculated, can determine in effective travel segment influence mileage travelled because
Element, so that it is determined that influencing the major parameter that continual mileage calculates deviation.Divided by the characteristic signal to effective travel segment
Analysis calculates to predict continual mileage, more representative, is conducive to the accuracy rate for promoting prediction.
Specifically, the continual mileage calculation formula is：
Y=a+b1x1+b2x2+b3x3+...b10x10；
Wherein, y indicates that continual mileage, a indicate the weighted value of mileage travelled；x1~x10Energy recovery rate, hundred are indicated respectively
Kilometer power of motor, hypervelocity rate, starting state-of-charge, state-of-charge variable quantity, automobile positive temperature coefficient ptc heater time account for
Than, electric theft-proof system EAS times accounting, battery mean temperature, environment mean temperature and road conditions average speed；b1~b10Point
It Biao Shi not energy recovery rate, hundred kilometers of powers of motor, hypervelocity rate, starting state-of-charge, state-of-charge variable quantity, the positive temperature of automobile
FACTOR P TC heater times accounting, electric theft-proof system EAS times accounting, battery mean temperature, environment mean temperature and road
The weighted value of condition average speed.
In the embodiment, when carrying out continual mileage prediction, it would be desirable to described in the trial value of the characteristic index of consideration substitutes into
Continual mileage calculation formula, you can obtain comprising the continual mileage under various factors.Wherein, before continual mileage prediction,
The precision of prediction of the continual mileage prediction technique can be verified, verification method is：It will be not engaged in car networking data
The data of characteristic index in the effective travel segment of regression model training substitute into the continual mileage calculation formula, can obtain
Prediction continual mileage after each Index Influence will predict the actual travel mileage of continual mileage and the effective travel segment
Comparison, by verification result it is found that prediction continual mileage and actual travel mileage deviation it is smaller, compared with the existing technology in pass through
Hundred kilometers of power consumptions carry out prediction continual mileage, and predictablity rate improves a lot.
As shown in figure 3, the embodiment provides a kind of continual mileage prediction meanss, including：
Signal extraction module 31 for dividing effective travel segment from the valid data in car networking pond, and is analyzed and is carried
It refers to the traveling segment that Vehicle Speed is more than zero to take correlated characteristic signal, the effective travel segment；
In the embodiment, the valid data refer in car networking pond all data through missing values handle, outlier processing
And the data obtained after the data cleansings such as record processing are repeated, the effective travel segment refers to that Vehicle Speed is more than zero
Traveling segment.After marking off effective travel segment in valid data, analysis is carried out to the data in effective travel segment and is carried
Relevant characteristic signal is taken out, i.e., the data information of vehicle really when driving is extracted from valid data, by these data
Information, which carries out correlation analysis, can obtain influencing the characteristic signal of continual mileage, to predict continual mileage, with more representative
Property, be conducive to the accuracy rate for promoting prediction.
Specifically, the characteristic signal includes：Power battery charging electric current, power battery charging voltage, power battery are put
Electric current, power battery discharge voltage, driving motor current torque, driving motor current rotating speed, mileage travelled, speed, the time,
Power battery charged state SOC, automobile positive temperature coefficient ptc heater state, electric theft-proof system EAS states, battery are average
Temperature and environment mean temperature.
First computing module 32, for multiple characteristic indexs to be calculated according to the characteristic signal；
Specifically, the characteristic index includes：Energy recovery rate, hundred kilometers of powers of motor, hypervelocity rate, the charged shape of starting
State, state-of-charge variable quantity, automobile positive temperature coefficient ptc heater time accounting, electric theft-proof system EAS times accounting, electricity
Pond mean temperature, environment mean temperature, road conditions average speed and mileage travelled.
The characteristic index is to calculate the influence factor being affected to continual mileage, and the characteristic index is by effective row
Characteristic signal in journey segment is calculated, and the computational methods that characteristic index is calculated according to characteristic signal are as shown in the table：
First structure module 33, the regression model for building the characteristic index utilize the data of the characteristic signal
The regression model is trained, the weighted value of the characteristic index is obtained；
Second structure module 34, for building continual mileage calculation formula according to the weighted value；
Second computing module 35 is obtained for the trial value of the characteristic index to be substituted into the continual mileage calculation formula
To continual mileage.
In the embodiment, it is contemplated that the shadow of other characteristic indexs can not be rejected when the correction factor of extraction single feature index
It rings, such as when air-conditioning unlatching, the other factors such as driver style, environment temperature and road conditions can all influence in current driving
Journey, so continual mileage prediction is carried out using regression combination model.Regression combination model algorithm is approximate correct based on probability
Learning model under a kind of boosting algorithm for proposing.In regression problem, built-up pattern is divided by changing the weights of training sample
Cloth learns multiple weak recurrence devices, and these is returned to device and carries out linear combination, constitutes one strong recurrence device, improves and return performance.
Device is wherein returned by force and can be regarded as the high algorithm of regression forecasting accuracy, and weak recurrence device can be regarded as the low algorithm of regression accuracy.
The characteristics of regression combination model algorithm is to learn a basic recurrence device (i.e. weak recurrence device) every time by iteration.Each iteration
In, it improves those and is returned the weights of device bigger error data sample by previous round, and reduce those and be predicted the small data of error
The weights of sample.Last algorithm returns device using the basic linear combination for returning device as strong, wherein the base small to error rate is returned
This recurrence device is with big weights, to the big basic recurrence device of recurrence error rate with small weights.
The sample that the program trains characteristic index as regression model, using the data of the characteristic signal to returning mould
Type is trained, and can obtain the proportion that different characteristic index accounts in mileage travelled, the i.e. weight of characteristic index, the feature
The weight of index is the coefficient in continual mileage calculation formula, it is known that the coefficient in continual mileage calculation formula can obtain
The function formula of continual mileage, when carrying out continual mileage prediction, it would be desirable to described in the trial value of the characteristic index of consideration substitutes into
Continual mileage calculation formula, you can obtain comprising the continual mileage under various factors.
The corresponding method of continual mileage prediction meanss compared to the prior art according to hundred kilometers of power consumptions to carry out prediction continuous
Mileage is sailed, the program carries out analysis modeling to a large amount of historical datas using big data platform, can significantly reduce electric vehicle
Continual mileage calculates deviation, carries out recurrence calculating in conjunction with current power consumption factor data, obtains best continual mileage predicted value, is promoted
Precision of prediction.
As shown in figure 4, the continual mileage prediction meanss further include：
Data extraction module 301 is used for from the data sample extracted in car networking pond in vehicle travel；
Cleaning module 302, for being cleaned to obtain valid data to the data sample.
In the embodiment, data pick-up and data cleansing are carried out based on car networking big data platform, taken out from car networking pond
Take the data sample in vehicle travel that increment extraction mechanism, increment extraction can be utilized to be carried out by the way of comparing timestamp,
The timestamp field of maximum time stamp and extraction source table when extraction process was extracted by comparing system time or source table last time
Value determine to extract which data.
Specifically, the cleaning module 302 is specifically used for：
Missing values, exceptional value and the repetition record cleaned in the data sample obtains valid data.
Wherein, the method for the missing values cleaned in the data sample is：Average value, maximum are generally used for missing values
Value, minimum value are replaced, but for car networking data rolling average may be used herein due to the particularity of time series
Algorithm, filtering algorithm or according to business rule come the value for missing of substituting, to achieve the purpose that cleaning.
Detection and cleaning method for exceptional value are：Possible error value or exception are identified with the method for statistical analysis
Value can also use simple rule library (common-sense rule, business if the value of distribution or regression equation is not abided by variance analysis, identification
Ad hoc rules etc.) check data value, or detect and clear up data using constraining between different attribute, external data.
It repeats the detection recorded and cleaning method is：The identical record of attribute value is considered as repeating to record in database,
By judging whether the attribute value between record is whether equal equal to detect record, and equal record merges into a record, i.e.,
Merge or removes.
As shown in figure 4, the signal extraction module 31 includes：
Segment division unit 311 divides for carrying out segment cutting to vehicle travel, determines effective travel segment；
Extraction unit 312 obtains multiple influences for carrying out correlation analysis to the data in the effective travel segment
The characteristic signal of continual mileage.
In the embodiment, due in car networking data, owning with what is do not travelled including vehicle travels within a period
Data, within this time, the segment of vehicle traveling can be solely a part, be drawn by carrying out segment cutting to vehicle travel
Point, it may be determined that the segment that vehicle really travels, i.e. effective travel segment, extraction effective travel segment includes out of valid data
Data, then the data that include on effective travel segment carry out correlation analysis and can obtain influencing the feature of continual mileage believing
Number, according to characteristic signal analysis characteristic index is calculated, can determine in effective travel segment influence mileage travelled because
Element, so that it is determined that influencing the major parameter that continual mileage calculates deviation.Divided by the characteristic signal to effective travel segment
Analysis calculates to predict continual mileage, more representative, is conducive to the accuracy rate for promoting prediction.
In the above embodiment of the present invention, the continual mileage calculation formula is：
Y=a+b1x1+b2x2+b3x3+...b10x10；
Wherein, y indicates that continual mileage, a indicate the weighted value of mileage travelled；x1~x10Energy recovery rate, hundred are indicated respectively
Kilometer power of motor, hypervelocity rate, starting state-of-charge, state-of-charge variable quantity, automobile positive temperature coefficient ptc heater time account for
Than, electric theft-proof system EAS times accounting, battery mean temperature, environment mean temperature and road conditions average speed；b1~b10Point
It Biao Shi not energy recovery rate, hundred kilometers of powers of motor, hypervelocity rate, starting state-of-charge, state-of-charge variable quantity, the positive temperature of automobile
FACTOR P TC heater times accounting, electric theft-proof system EAS times accounting, battery mean temperature, environment mean temperature and road
The weighted value of condition average speed.
In the embodiment, when carrying out continual mileage prediction, it would be desirable to described in the trial value of the characteristic index of consideration substitutes into
Continual mileage calculation formula, you can obtain comprising the continual mileage under various factors.Wherein, before continual mileage prediction,
The precision of prediction of the continual mileage prediction technique can be verified, verification method is：It will be not engaged in car networking data
The data of characteristic index in the effective travel segment of regression model training substitute into the continual mileage calculation formula, can obtain
Prediction continual mileage after each Index Influence will predict the actual travel mileage of continual mileage and the effective travel segment
Comparison, by verification result it is found that prediction continual mileage and actual travel mileage deviation it is smaller, compared with the existing technology in pass through
Hundred kilometers of power consumptions carry out prediction continual mileage, and predictablity rate improves a lot.
It should be noted that the device is device corresponding with above-mentioned individual recommendation method, institute in above method embodiment
There is realization method suitable for the embodiment of the device, can also reach identical technique effect.
The embodiment provides a kind of pre- measurement equipment of continual mileage, processor, memory and it is stored in described deposit
On reservoir and the computer program that can run on the processor, the computer program are realized when being executed by the processor
The step of above-mentioned continual mileage prediction technique.It should be noted that the equipment is that recommendation method is corresponding sets with above-mentioned individual
Standby, all realization methods can also reach identical technology effect suitable for the embodiment of the equipment in above method embodiment
Fruit.
The embodiment of the present invention influences the master of continual mileage deviation by being determined on the data mining of car networking big data
Want parameter, based on a large amount of historical datas carry out regression model training, promoted predictablity rate, in conjunction with current power consumption factor data into
Row, which returns, to be calculated, it can be deduced that best continual mileage predicted value improves precision of prediction.
Above-described is the preferred embodiment of the present invention, it should be pointed out that the ordinary person of the art is come
It says, can also make several improvements and retouch under the premise of not departing from principle of the present invention, these improvements and modifications also exist
In protection scope of the present invention.
Claims (15)
1. a kind of continual mileage prediction technique, which is characterized in that including：
Effective travel segment is divided from the valid data in car networking pond, and analyzes extraction correlated characteristic signal, it is described effective
Stroke segment refers to the traveling segment that Vehicle Speed is more than zero；
Multiple characteristic indexs are calculated according to the characteristic signal；
The regression model for building the characteristic index is trained the regression model using the data of the characteristic signal, obtains
To the weighted value of the characteristic index；
Continual mileage calculation formula is built according to the weighted value；
The trial value of the characteristic index is substituted into the continual mileage calculation formula, obtains continual mileage.
2. continual mileage prediction technique according to claim 1, which is characterized in that effective in the pond from car networking
Effective travel segment is divided in data, and before the step of analyzing extraction correlated characteristic signal, the method further includes：
From the data sample extracted in car networking pond in vehicle travel；
The data sample is cleaned to obtain valid data.
3. continual mileage prediction technique according to claim 2, which is characterized in that the data sample clean
Include to the step of valid data：
Missing values, exceptional value and the repetition record cleaned in the data sample obtains valid data.
4. continual mileage prediction technique according to claim 1, which is characterized in that from the valid data in car networking pond
Effective travel segment is divided, and the step of analyzing extraction correlated characteristic signal includes：
Segment cutting is carried out to vehicle travel to divide, and determines effective travel segment；
Correlation analysis is carried out to the data in the effective travel segment, obtains multiple characteristic signals for influencing continual mileage.
5. continual mileage prediction technique according to claim 1, which is characterized in that the characteristic signal includes：Power electric
Pond charging current, power battery charging voltage, power battery discharge current, power battery discharge voltage, driving motor work as forward
Square, driving motor current rotating speed, mileage travelled, speed, time, power battery charged state SOC, automobile positive temperature coefficient PTC
Heater status, electric theft-proof system EAS states, battery mean temperature and environment mean temperature.
6. continual mileage prediction technique according to claim 1, which is characterized in that the characteristic index includes：Energy returns
Yield, hundred kilometers of powers of motor, hypervelocity rate, starting state-of-charge, state-of-charge variable quantity, the PTC heating of automobile positive temperature coefficient
Device time accounting, electric theft-proof system EAS times accounting, battery mean temperature, environment mean temperature, road conditions average speed and
Mileage travelled.
7. continual mileage prediction technique according to claim 6, which is characterized in that the continual mileage calculation formula is：
Y=a+b1x1+b2x2+b3x3+...b10x10；
Wherein, y indicates that continual mileage, a indicate the weighted value of mileage travelled；x1~x10Respectively indicate energy recovery rate, hundred kilometers
Power of motor, hypervelocity rate, starting state-of-charge, state-of-charge variable quantity, automobile positive temperature coefficient ptc heater time accounting,
Electric theft-proof system EAS times accounting, battery mean temperature, environment mean temperature and road conditions average speed；b1~b10Respectively
Indicate energy recovery rate, hundred kilometers of powers of motor, hypervelocity rate, starting state-of-charge, state-of-charge variable quantity, the positive temperature system of automobile
Number ptc heater time accounting, electric theft-proof system EAS times accounting, battery mean temperature, environment mean temperature and road conditions
The weighted value of average speed.
8. a kind of continual mileage prediction meanss, which is characterized in that including：
Signal extraction module, for dividing effective travel segment from the valid data in car networking pond, and it is related to analyze extraction
Characteristic signal, the effective travel segment refer to the traveling segment that Vehicle Speed is more than zero；
First computing module, for multiple characteristic indexs to be calculated according to the characteristic signal；
First structure module, the regression model for building the characteristic index, using the data of the characteristic signal to this time
Return model to be trained, obtains the weighted value of the characteristic index；
Second structure module, for building continual mileage calculation formula according to the weighted value；
Second computing module obtains driving for the trial value of the characteristic index to be substituted into the continual mileage calculation formula
Mileage.
9. continual mileage prediction meanss according to claim 8, which is characterized in that the continual mileage prediction meanss are also wrapped
It includes：
Data extraction module is used for from the data sample extracted in car networking pond in vehicle travel；
Cleaning module, for being cleaned to obtain valid data to the data sample.
10. continual mileage prediction meanss according to claim 9, which is characterized in that the cleaning module is specifically used for：
Missing values, exceptional value and the repetition record cleaned in the data sample obtains valid data.
11. continual mileage prediction meanss according to claim 8, which is characterized in that the signal extraction module includes：
Segment division unit divides for carrying out segment cutting to vehicle travel, determines effective travel segment；
Extraction unit is obtained for carrying out correlation analysis to the data in the effective travel segment in multiple influence drivings
The characteristic signal of journey.
12. continual mileage prediction meanss according to claim 8, which is characterized in that the characteristic signal includes：Power electric
Pond charging current, power battery charging voltage, power battery discharge current, power battery discharge voltage, driving motor work as forward
Square, driving motor current rotating speed, mileage travelled, speed signal, time, power battery charged state SOC, automobile positive temperature coefficient
Ptc heater state, electric theft-proof system EAS states, battery mean temperature and environment mean temperature.
13. continual mileage prediction meanss according to claim 8, which is characterized in that the characteristic index includes：Energy returns
Yield, hundred kilometers of powers of motor, hypervelocity rate, starting state-of-charge, state-of-charge variable quantity, the PTC heating of automobile positive temperature coefficient
Device time accounting, electric theft-proof system EAS times accounting, battery mean temperature, environment mean temperature, road conditions average speed and
Mileage travelled.
14. continual mileage prediction meanss according to claim 13, which is characterized in that the continual mileage calculation formula
For：
Y=a+b1x1+b2x2+b3x3+...b10x10；
Wherein, y indicates that continual mileage, a indicate the weighted value of mileage travelled；x1~x10Respectively indicate energy recovery rate, hundred kilometers
Power of motor, hypervelocity rate, starting state-of-charge, state-of-charge variable quantity, automobile positive temperature coefficient ptc heater time accounting,
Electric theft-proof system EAS times accounting, battery mean temperature, environment mean temperature and road conditions average speed；b1~b10Respectively
Indicate energy recovery rate, hundred kilometers of powers of motor, hypervelocity rate, starting state-of-charge, state-of-charge variable quantity, the positive temperature system of automobile
Number ptc heater time accounting, electric theft-proof system EAS times accounting, battery mean temperature, environment mean temperature and road conditions
The weighted value of average speed.
15. a kind of pre- measurement equipment of continual mileage, which is characterized in that including processor, memory and be stored on the memory
And the computer program that can be run on the processor, such as right is realized when the computer program is executed by the processor
It is required that the step of continual mileage prediction technique described in any one of 1~7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810294117.3A CN108556682B (en) | 2018-03-30 | 2018-03-30 | Driving range prediction method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810294117.3A CN108556682B (en) | 2018-03-30 | 2018-03-30 | Driving range prediction method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108556682A true CN108556682A (en) | 2018-09-21 |
| CN108556682B CN108556682B (en) | 2020-06-02 |
Family
ID=63533980
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810294117.3A Active CN108556682B (en) | 2018-03-30 | 2018-03-30 | Driving range prediction method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108556682B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784560A (en) * | 2019-01-15 | 2019-05-21 | 深圳四海万联科技有限公司 | A kind of electric car course continuation mileage evaluation method and estimating system |
| CN111619356A (en) * | 2019-02-28 | 2020-09-04 | 北京新能源汽车股份有限公司 | Charging control method, device and system and automobile |
| CN111739286A (en) * | 2020-05-15 | 2020-10-02 | 南斗六星系统集成有限公司 | Travel analysis method and device based on vehicle speed state |
| CN112782584A (en) * | 2019-11-05 | 2021-05-11 | 奥动新能源汽车科技有限公司 | Method, system, medium, and device for predicting remaining usage limit of battery power |
| CN113085592A (en) * | 2021-04-12 | 2021-07-09 | 中山大学 | Method and system for predicting driving range of hydrogen fuel cell dump truck in real time |
| CN113159435A (en) * | 2021-04-29 | 2021-07-23 | 浙江吉利控股集团有限公司 | Method and system for predicting remaining driving mileage of new energy vehicle |
| CN113167837A (en) * | 2018-11-30 | 2021-07-23 | 康明斯公司 | Vehicle driving range estimator |
| CN113335131A (en) * | 2020-02-18 | 2021-09-03 | 宁波吉利汽车研究开发有限公司 | Vehicle endurance mileage prediction method, device, equipment and storage medium |
| CN116340767A (en) * | 2023-02-27 | 2023-06-27 | 吉林大学 | Electric automobile travel energy consumption probability distribution prediction method, system and product |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102745201A (en) * | 2012-06-30 | 2012-10-24 | 惠州市亿能电子有限公司 | Estimation method for remainder mileage of electric automobile |
| CN105292126A (en) * | 2015-10-21 | 2016-02-03 | 北京新能源汽车股份有限公司 | Electric automobile driving range estimation method and device and electric automobile |
| US20160114698A1 (en) * | 2014-10-28 | 2016-04-28 | North Carolina State University | Method and apparatus for analyzing data related to vehicle range estimation |
| CN105539446A (en) * | 2015-12-21 | 2016-05-04 | 东软集团股份有限公司 | Method and device for predicating driving mileage |
| CN106427589A (en) * | 2016-10-17 | 2017-02-22 | 江苏大学 | Electric car driving range estimation method based on prediction of working condition and fuzzy energy consumption |
| CN106945530A (en) * | 2017-04-07 | 2017-07-14 | 重庆长安汽车股份有限公司 | A kind of electric automobile and its continual mileage Forecasting Methodology, system |
-
2018
- 2018-03-30 CN CN201810294117.3A patent/CN108556682B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102745201A (en) * | 2012-06-30 | 2012-10-24 | 惠州市亿能电子有限公司 | Estimation method for remainder mileage of electric automobile |
| US20160114698A1 (en) * | 2014-10-28 | 2016-04-28 | North Carolina State University | Method and apparatus for analyzing data related to vehicle range estimation |
| CN105292126A (en) * | 2015-10-21 | 2016-02-03 | 北京新能源汽车股份有限公司 | Electric automobile driving range estimation method and device and electric automobile |
| CN105539446A (en) * | 2015-12-21 | 2016-05-04 | 东软集团股份有限公司 | Method and device for predicating driving mileage |
| CN106427589A (en) * | 2016-10-17 | 2017-02-22 | 江苏大学 | Electric car driving range estimation method based on prediction of working condition and fuzzy energy consumption |
| CN106945530A (en) * | 2017-04-07 | 2017-07-14 | 重庆长安汽车股份有限公司 | A kind of electric automobile and its continual mileage Forecasting Methodology, system |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113167837A (en) * | 2018-11-30 | 2021-07-23 | 康明斯公司 | Vehicle driving range estimator |
| CN109784560A (en) * | 2019-01-15 | 2019-05-21 | 深圳四海万联科技有限公司 | A kind of electric car course continuation mileage evaluation method and estimating system |
| CN111619356A (en) * | 2019-02-28 | 2020-09-04 | 北京新能源汽车股份有限公司 | Charging control method, device and system and automobile |
| CN111619356B (en) * | 2019-02-28 | 2022-04-19 | 北京新能源汽车股份有限公司 | Charging control method, device and system and automobile |
| CN112782584A (en) * | 2019-11-05 | 2021-05-11 | 奥动新能源汽车科技有限公司 | Method, system, medium, and device for predicting remaining usage limit of battery power |
| CN113335131A (en) * | 2020-02-18 | 2021-09-03 | 宁波吉利汽车研究开发有限公司 | Vehicle endurance mileage prediction method, device, equipment and storage medium |
| CN111739286A (en) * | 2020-05-15 | 2020-10-02 | 南斗六星系统集成有限公司 | Travel analysis method and device based on vehicle speed state |
| CN111739286B (en) * | 2020-05-15 | 2023-10-13 | 南斗六星系统集成有限公司 | Stroke analysis method and device based on vehicle speed state |
| CN113085592A (en) * | 2021-04-12 | 2021-07-09 | 中山大学 | Method and system for predicting driving range of hydrogen fuel cell dump truck in real time |
| CN113085592B (en) * | 2021-04-12 | 2024-04-12 | 中山大学 | Method and system for predicting driving range of hydrogen fuel cell dump truck in real time |
| CN113159435A (en) * | 2021-04-29 | 2021-07-23 | 浙江吉利控股集团有限公司 | Method and system for predicting remaining driving mileage of new energy vehicle |
| CN113159435B (en) * | 2021-04-29 | 2022-11-22 | 浙江吉利控股集团有限公司 | Method and system for predicting remaining driving mileage of new energy vehicle |
| CN116340767A (en) * | 2023-02-27 | 2023-06-27 | 吉林大学 | Electric automobile travel energy consumption probability distribution prediction method, system and product |
| CN116340767B (en) * | 2023-02-27 | 2023-12-01 | 吉林大学 | Electric automobile travel energy consumption probability distribution prediction method, system and product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108556682B (en) | 2020-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108556682A (en) | Driving range prediction method, device and equipment | |
| Modi et al. | Estimation of energy consumption of electric vehicles using deep convolutional neural network to reduce driver’s range anxiety | |
| CN107862864A (en) | Driving cycle intelligent predicting method of estimation based on driving habit and traffic | |
| Guo et al. | A novel energy consumption prediction model with combination of road information and driving style of BEVs | |
| Bi et al. | Residual range estimation for battery electric vehicle based on radial basis function neural network | |
| CN111038334A (en) | Method and device for predicting driving range of electric automobile | |
| CN106427589A (en) | Electric car driving range estimation method based on prediction of working condition and fuzzy energy consumption | |
| CN109784560A (en) | A kind of electric car course continuation mileage evaluation method and estimating system | |
| CN105868787A (en) | Electric car driving range evaluation method based on working condition identification and fuzzy energy consumption | |
| CN104408924B (en) | A kind of urban road abnormal traffic stream detection method based on coupled hidden markov model | |
| CN107037370A (en) | Residual quantity calculation method of electric vehicle battery based on monitoring data | |
| Fan et al. | Predicting vacant parking space availability: a long short-term memory approach | |
| CN116572799B (en) | Power battery charge duration prediction method, system and terminal based on deep learning | |
| CN113159435B (en) | Method and system for predicting remaining driving mileage of new energy vehicle | |
| CN110738855A (en) | Road traffic flow condition prediction method for data sparse time periods | |
| CN106956680A (en) | A kind of electric automobile driving behavior identifying and analyzing method | |
| CN115063184A (en) | Electric vehicle charging demand modeling method, system, medium, equipment and terminal | |
| CN109637128A (en) | A kind of grey Verhulst Short-time Traffic Flow Forecasting Methods and system based on Markov | |
| CN115759462A (en) | Charging behavior prediction method and device for electric vehicle user and electronic equipment | |
| CN115219913A (en) | Power battery full-life-cycle management system based on capacity increment method | |
| CN114676870A (en) | Vehicle speed prediction method, vehicle speed prediction model training method and related device | |
| CN109117972A (en) | A kind of charge requirement of electric car determines method | |
| CN113525385A (en) | Method and device for predicting vehicle travel energy consumption | |
| CN110852378A (en) | Road condition kinematics segment extraction method based on navigation system | |
| CN116824520A (en) | Vehicle track prediction method and system based on ReID and graph convolution network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |